MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
An async multi-agent learning roadmap planner built with LangChain, LangGraph, Tavily, and a custom FastMCP course server.
-
Local institutional learning engine for AI agents — capture, curate, and publish reusable learnings via MCP
MIT ★ 7 -
@satyam1990/learn-mcpupdated this year
A simple MCP server that learns from the user with Google AI SDK
npm MIT -
vibe-learninggithub.com/12OneTwo12/vibe-learningupdated this year
MCP server that helps you actually learn while vibe coding with AI
MIT ★ 1 -
Local-first learning state layer and MCP connector for AI agents.
MIT ★ 1 -
language-learning-mcpgithub.com/MahammadNuriyev62/language-learning-mcpupdated this year
Interactive language learning MCP App for Claude.ai with 10 exercise types
-
learn-mcpgithub.com/fvegiard/learn-mcpupdated this year
AI Engineering Learning Reference MCP Server — 550+ searchable references for MCP, RAG, agents, fine-tuning, MLOps, prompt engineering, inference, vector DBs, GPU compute, autonomous agents, and Claude Code workflows
MIT -
Vibe learn anything: your AI agent turns an article, doc, or code into a short interactive lesson with a shareable link.
Apache-2.0 ★ 6 -
DTU Learn MCP server and API client: use your DTU Learn (Brightspace/D2L) courses, deadlines, slides and Panopto lecture transcripts with Claude and other AI assistants. Unofficial student project.
MIT -
Built an AI-driven workflow that generates personalized learning paths from user prompts. Also Automated fetching of relevant YouTube content and saved curated learning plans to Google Drive via MCP server integrations.
-
The official Clozemaster CLI: learn languages in your terminal, with a built-in MCP server for AI assistants.
MIT ★ 5 -
Local-first personal knowledge management (PKM) MCP server and learning memory for every AI tutor—goal trees, a reusable knowledge graph, and evidence-gated mastery.
mcpb Apache-2.0 -
Self-learning AI standards system - learns from corrections and auto-updates CLAUDE.md
pypi MIT -
Learn AI from the people building it: a YouTube + X learning feed with Shorts, hands-on labs, books, papers and an MCP connector.
MIT -
An MCP server enabling guided DSA learning with AI on leetcode.com
npm MIT ★ 12 -
learndeckgithub.com/learn-deck/learndeckupdated this year
A local, open-source learning app with AI guides, Markdown courses, and MCP.
Apache-2.0 -
Pathly AI — Personalized Learning Roadmaps, Skill Assessment & Progress Tracking | React + FastAPI + MCP
-
mindkeg-mcpgithub.com/carloluisito/mindkeg-mcpupdated this year
A persistent memory MCP server for AI coding agents — stores, searches, and retrieves atomic learnings per repository.
npm MIT -
Flashcards and quiz questions as a learning page for vocational school. The teacher creates learning bundles through an AI agent (MCP), the class opens a three-word link – no sign-in, no stored results.
MIT ★ 1 -
AI-powered IT Helpdesk system with ticket prediction, FastAPI, PostgreSQL, MCP, and machine learning.
-
synaptic-memoryupdated this year
Human-like neural memory system - Neuron-based persistent memory with Hebbian learning for AI agents
npm MIT -
Murphys Law — a lessons-learned register for AI agent fleets. Whatever can go wrong, will — once. MCP server + CLI.
MIT -
An Agent-Computer Interface (ACI) for AI-driven machine learning.
pypi MIT ★ 4 -
Java employee-leave AI learning project using Spring AI, Gemini, RAG, tool calling, and an MCP server.
-
CLI and SDK for π — the RuVector shared brain. Share, search, and transfer learning across AI sessions.
npm MIT -
An English-learning adaptation of Xiaozhi for Waveshare ESP32-S3 AMOLED: an on-screen character and vocabulary cards triggered by AI through MCP.
MIT -
graphonomousgithub.com/c-u-l8er/graphonomousupdated this year
Continual learning MCP server for AI agents — topology-aware knowledge graph with kappa-routing, exposed as 5 loop-phase machines (retrieve/route/act/learn/consolidate), causal metadata, and neural embeddings. One of four MCP servers in the [&] three-prot
npm Apache-2.0 -
Learn the Greek hiding in everyday English, in 3-minute lessons. Web app + MCP server so your AI agent can tutor you.
MIT ★ 5 -
long-term-memorygithub.com/ihwoomil/long-term-memoryupdated this year
Long-term memory system for AI assistants — persistent, searchable, self-organizing memory powered by semantic search, knowledge graphs, and reinforcement learning
pypi MIT -
Make every AI agent you use smarter. Persistent memory with SQLite FTS5, MCP server, Obsidian sync, and self-learning intelligence pipeline.
MIT ★ 190 -
Map and manage human skills with a structured system designed to track learning and development alongside AI capabilities.
-
telegram-ai-agentgithub.com/abailey81/telegram-ai-agentupdated this year
Production-grade conversational AI platform — 13 intelligence engines, 6 deep learning models, Thompson sampling RL, 4-backend voice synthesis, and autonomous model improvement. 90+ MCP tools, 80+ REST endpoints.
Apache-2.0 ★ 3 -
skill-router-g6github.com/ForYourHelpAI101/skill-router-g6updated this year
Self-learning skill router for AI agents. 6-stage pipeline with anti-hallucination protections. Model-agnostic MCP server.
MIT -
@iflow-mcp/ahmedraoofuddin-cortivexgithub.com/ahmedraoofuddin/cortivexupdated this year
AI agent pipeline orchestration with Claude Code skills, self-learning workflows, and zero-infrastructure coordination.
npm MIT -
MCP server that turns your latest commits into hand-drawn Excalidraw diagrams of the concepts they use, so you keep learning from code your AI wrote.
npm PolyForm-Noncommercial-1.0.0 -
MCP server for Vocabit — let an AI assistant build flashcard sets inside a real language-learning app and read back how the learner actually did.
npm MIT -
Intelligent-LMS-Agentgithub.com/AsmaAlkayali/Intelligent-LMS-Agentupdated this year
LLM-powered academic assistant integrating AI Agents, Model Context Protocol (MCP), Retrieval-Augmented Generation (RAG), and FastAPI for intelligent learning management.
-
Local-first AI/ML research curation: Quick Search, Learning Path, Research Lineage, Trending Feed, My Feed, Venues. Data from Semantic Scholar, HuggingFace, GitHub. MCP server included.
MIT ★ 2 -
A no code AI data science copilot. Point it at a spreadsheet and it runs the whole machine learning workflow, then explains the result in plain language. Built with scikit learn, LangGraph, RAG, and MCP, with a leakage safe pipeline and a human in the loop.
MIT ★ 1 -
NextStep-AIgithub.com/satish-goud/NextStep-AIupdated this year
AI-powered career guidance platform using Streamlit, Gemini AI, Multi-Agent Architecture, and MCP to analyze resumes, identify skill gaps, and generate personalized learning roadmaps.
-
AI/ML production readiness auditing. A remote MCP server that audits machine-learning projects for the issues that cause production incidents.
Apache-2.0 -
breezemlgithub.com/venomez-viper/breezemlupdated this year
A beginner-friendly, production-aware ML workflow layer for students, analysts, and AI agents. Train, compare, explain, export, and deploy scikit-learn models without the boilerplate.
MIT ★ 3 -
Enterprise-grade Machine Learning experimentation control plane for AI agents via Model Context Protocol (MCP). Train, validate, and diagnose 7 tabular architectures (LightGBM, XGBoost, CatBoost, RF, SVM, MLP) with zero arbitrary code execution.
★ 1 -
Transform GitHub Copilot into a sophisticated AI learning partner with meta-cognitive awareness, persistent memory, dual-mind processing, and cross-project knowledge sharing. VS Code extension.
npm NOASSERTION ★ 4 -
MCP server for Vocabit: an AI assistant builds a flashcard set inside a real language-learning app, then reads back how the learner actually did. Ships with a no-backend demo mode.
npm MIT -
Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contradiction detection, prospective triggers, Bayesian calibration, zero-config Docker setup.
npm Apache-2.0 ★ 30 -
Agent-first adaptive learning platform. Create courses as YAML knowledge graphs via CLI or MCP server. AI agents scaffold, fill, review, and publish — no UI required. Adaptive diagnostics, spaced repetition, white-label sites.
npm NOASSERTION ★ 3 -
Kubernetes, Helm, OpenShift, ROSA HCP and RHACS expertise as deterministic tools: audit, diagnose, cited search, learning. No AI inside: use it from Claude, OpenShift Lightspeed, any MCP client or the CLI.
pypi Apache-2.0 -
Build with AI, learn like a real engineer. Local-first: import a repo → senior-grade deep review, architecture map, code-grounded DSA, and explain-back questions. 127.0.0.1, no telemetry.
NOASSERTION -
Robot learning stack for a real WidowX AI arm: demo capture, calibrated MuJoCo digital twin, Diffusion Policy with real-time chunking, π₀.₅/LeRobot in Docker, and LLM tool-calling control over MCP.
NOASSERTION -
Learn what you don't know yet from the code your AI agent writes. Free and secure by design, for Claude Code, Claude Desktop, Gemini CLI & Codex — one lesson at a time.
npm AGPL-3.0 ★ 5 -
物理约束的能带结构 MCP 服务器:让 AI 读取论文/实验能带图与数值能带,提供检索、匹配与可信拒识的开源工具。A physics-aware band-structure MCP server for AI agents (Docker, stdio/HTTP, MIT). Built with AI-agent assistance by a mechanical-engineering student as a DFT-learning project.
MIT -
MwalimuLens is an evidence-grounded educational AI agent that analyses learning records across terms, identifies potential competency patterns and prepares source-linked insights for teacher review, with human oversight and safeguards against premature learner judgements.
Apache-2.0 -
Issue router that learns which team owns what from the issues that actually get fixed. Weighted path search on a HydraDB graph, a React dashboard, and an MCP server for AI agents.
GPL-3.0 ★ 1 -
Decentralized AI Memory Network (DAMN) — a persistent learning and memory-sharing infrastructure for autonomous agents. Blockchain + IPFS-based memory layer enabling cross-agent experience reuse and scalable distributed intelligence.
★ 1 -
Machine-learning oral drug-likeness score for small molecules (SMILES in, 0–1 out), with an MCP server for AI assistants (Claude, Cursor, VS Code and other MCP clients). J. Chem. Inf. Model. 2026.
pypi MIT ★ 4 -
Long-term memory MCP server for OpenCode and other harnesses — stores preferences, lessons, and usage history in a single local SQLite file (100% local, no external API) so the AI can "remember and adapt" to the user through context-based learning.
npm MIT ★ 3 -
Instagram-style media sharing platform built to learn distributed systems: Envoy gateway, Kafka + transactional outbox, presigned S3 uploads, OIDC/PKCE, SSE, rate limiting, tracing, an MCP server for AI assistants (token exchange), and webhook-driven subscriptions. Runs on Docker Compose.
-
☀️Helios MCP: Give your AI permanent memory & personality! Install once, AI remembers forever. No more repeating context through versioned memory, behavioral & pattern learning, and multi-agent sync. UV-powered FastMCP server to teach your AI preferences and working styles that evolve through usage. Not a RAG system! Try today!☀️
MIT ★ 2 -
ML Referee evaluates whether candidate features add predictive value beyond a baseline for machine learning and forecasting. AI agents can preflight data, request quotes, and run authorized evaluations through MCP. Invite-only beta. Website: MCP endpoint: https://api.mlreferee.com/mcp
MIT